© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 11572
    Prev
    Next
    INDEX
    Explanations

    obsidian ppv method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    b
    1.20
    िव
    1.14
    ﺝ
    1.11
     quatre
    1.09
     four
    1.09
     six
    1.08
    h
    1.07
    ﺽ
    1.07
     deux
    1.04
     ஒன்றிய
    1.03
    POSITIVE LOGITS
    Whenever
    1.09
     насколько
    1.09
     Međutim
    1.09
     Although
    1.06
    Although
    1.05
    However
    1.04
    Because
    1.03
     whenever
    1.01
    Ī
    1.00
     Whenever
    1.00
    Activations Density 0.073%

    No Known Activations